© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5389
    Prev
    Next
    INDEX
    Explanations

    disclaimers and liability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦ人éĥ½
    -0.09
    訾
    -0.09
     puberty
    -0.09
    秩
    -0.09
    æľºä¼ļ
    -0.09
    /license
    -0.08
    /gpl
    -0.08
    åįłæľī
    -0.08
    订
    -0.08
    _INITIALIZER
    -0.08
    POSITIVE LOGITS
    arial
    0.10
    让å®ĥ
    0.08
    éĺģ
    0.08
    ä¸ĩäºĭ
    0.08
    mediate
    0.08
    æĥ³ä¸įåĪ°
    0.08
    éĴ¦
    0.08
    对æѤ
    0.08
    殿
    0.08
    ugen
    0.08
    Activations Density 0.014%

    No Known Activations